Summary plots - Sample strategy is on the y-axis and number of sites is on the x-axis. Each plot is paired by parameter level vertically and the values in the cells are the mean value across all of the simulations for that parameter level. Note that each average encompasses all of the other varying simulation parameters as seen in the Full plots.

Full plots - For the full plots, Each plot represents a unique simulation and the values in the cells are the mean value across all of the 10 iterations of that simulation across all three unique landscape seeds (i.e., all three sets of Neutral Landscape Models) for a total of 30 replicates. Sample strategy is on the y-axis and number of sites is on the x-axis. Since there are a many simulations presented in the full plots, here is a handy key for how the different parameters are laid out within them (H = High, L = Low):

TPR - True Positive Rate. The proportion of times there was a positive detection in both the sub-sampled model and the full model. Note that in the case of GDM TPR is frequently NA because there was no detection in the full model.

FDR - False Discovery Rate. The proportion of times there was a detection in the sub-sampled model that was not shared with the full model.

ME - mean error was calculated by taking the mean difference between the observed and expected coefficients, because the absolute value is not taken this measurement is used to determine whether over- or underestimation is occurring. For IBE ME the two environmental coefficient errors were averaged.

MAE - mean absolute error calculated as the difference between the observed and expected coefficients. For IBE MAE the two environmental coefficient errors were averaged.

Proportion of negative & significant coefficients - this only applies to MMRR and IBE and is the proportion of coefficients that were negative & significant.

Proportion NA - this only applies to GDM and IBE and is the proportion of NA p-values due to the variable significance procedure note being able to be carried out because more than two variable coefficients in the model were zero or because one of the models used in the calculation could not be fit. Note that p-values would also be NA in the case of the variable coefficient was zero, but we treated these as cases of no detection in our calculation of TPR/FDR, whereas the other NA values were excluded.

1. MMRR

1.1 Individual sampling

1.1.1 Summary plots

1.1.2 Linear mixed effects models

## Warning in run_lmer(mmrr_ind, .x, filepath = make_lmer_path("mmrr", "ind", : 
## All values of IBD TPR are fixed or NA; no model is returned
## Warning in run_lmer(mmrr_ind, .x, filepath = make_lmer_path("mmrr", "ind", : 
## All values of IBD FDR are fixed or NA; no model is returned
Linear mixed effect model
IBD MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0001 1.2256 1.2256 1 15.3480K 1239.45785 3.5 × 10−261*
Population size 0.0074 0.2110 0.2110 1 15.3480K 213.43225 5.1 × 10−48*
Migration 0.0255 2.5010 2.5010 1 15.3480K 2529.24460 0.0*
Selection strength −0.0017 0.0117 0.0117 1 15.3480K 11.86573 5.7 × 10−4*
Spatial autocorrelation 0.0060 0.1360 0.1360 1 15.3480K 137.55767 1.2 × 10−31*
Environmental correlation −0.0017 0.0109 0.0109 1 15.3480K 11.04706 8.9 × 10−4*
* p < 0.001
Tukey test for IBD MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G −0.0029 0.0007 −4.0599 2.9 × 10−4
ES - R −0.0010 0.0007 −1.4344 0.47776346
ES - T −0.0246 0.0007 −34.3328 0.0
G - R 0.0019 0.0007 2.6255 0.04296249
G - T −0.0217 0.0007 −30.2729 0.0
R - T −0.0236 0.0007 −32.8984 0.0
Linear mixed effect model
IBE TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0017 169.6446 169.6446 1 11.8600K 1368.252072 1.5 × 10−283*
Population size −0.1035 31.5107 31.5107 1 11.8601K 254.146163 1.3 × 10−56*
Migration −0.3584 330.2984 330.2984 1 11.8601K 2663.989576 0.0*
Selection strength 0.0597 10.5688 10.5688 1 11.8601K 85.241941 3.1 × 10−20*
Spatial autocorrelation 0.3415 293.4664 293.4664 1 11.8603K 2366.924775 0.0*
Environmental correlation −0.0200 1.1842 1.1842 1 11.8600K 9.551297 2.0 × 10−3**
* p < 0.001
** p < 0.01
Tukey test for IBE TPR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G 0.1269 0.0091 13.8781 0.0
ES - R 0.0756 0.0091 8.2753 4.5 × 10−14
ES - T −0.0101 0.0091 −1.1058 0.6859408
G - R −0.0512 0.0091 −5.6029 1.3 × 10−7
G - T −0.1370 0.0091 −14.9840 0.0
R - T −0.0857 0.0091 −9.3811 3.8 × 10−14
Linear mixed effect model
IBE FDR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0001 1.0722 1.0722 1 15.3480K 46.924365 7.7 × 10−12*
Population size 0.0167 1.0667 1.0667 1 15.3480K 46.683954 8.7 × 10−12*
Migration 0.0182 1.2760 1.2760 1 15.3480K 55.847504 8.3 × 10−14*
Selection strength −0.0036 0.0510 0.0510 1 15.3480K 2.233900 0.14
Spatial autocorrelation −0.0413 6.5423 6.5423 1 15.3480K 286.329583 1.2 × 10−63*
Environmental correlation 0.0069 0.1829 0.1829 1 15.3480K 8.003859 4.7 × 10−3**
* p < 0.001
** p < 0.01
Tukey test for IBE FDR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G 0.0103 0.0034 2.9819 0.01519496
ES - R 0.0052 0.0034 1.5098 0.43153409
ES - T −0.0194 0.0034 −5.6240 1.1 × 10−7
G - R −0.0051 0.0034 −1.4721 0.45448499
G - T −0.0297 0.0034 −8.6058 3.6 × 10−14
R - T −0.0246 0.0034 −7.1338 5.9 × 10−12
Linear mixed effect model
IBE MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0002 2.4101 2.4101 1 15.3480K 3606.434014 0.0*
Population size 0.0037 0.0526 0.0526 1 15.3480K 78.639576 8.3 × 10−19*
Migration 0.0178 1.2102 1.2102 1 15.3480K 1810.842798 0.0*
Selection strength −0.0019 0.0134 0.0134 1 15.3480K 20.109804 7.4 × 10−6*
Spatial autocorrelation 0.0025 0.0241 0.0241 1 15.3480K 36.110285 1.9 × 10−9*
Environmental correlation 0.0007 0.0020 0.0020 1 15.3480K 2.978678 0.084
* p < 0.001
Tukey test for IBE MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G 0.0014 0.0006 2.3636 0.08420456
ES - R 0.0022 0.0006 3.6842 1.3 × 10−3
ES - T −0.0041 0.0006 −6.9400 2.4 × 10−11
G - R 0.0008 0.0006 1.3206 0.54973652
G - T −0.0055 0.0006 −9.3037 4.1 × 10−14
R - T −0.0063 0.0006 −10.6243 3.6 × 10−14

1.1.3 Full plots

1.2 Site sampling

1.2.1 Summary plots

1.2.2 Linear mixed effects models

Linear mixed effect model
IBD TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0001 0.0080 0.0080 1 8.6310K 8.619034e+00 3.3 × 10−3*
Population size −0.0009 0.0019 0.0019 1 8.6310K 2.003506e+00 0.16
Migration −0.0009 0.0019 0.0019 1 8.6310K 2.003506e+00 0.16
Selection strength 0.0005 0.0005 0.0005 1 8.6310K 5.008765e-01 0.48
Spatial autocorrelation −0.0009 0.0019 0.0019 1 8.6310K 2.003506e+00 0.16
Environmental correlation 0.0000 0.0000 0.0000 1 8.6310K 4.154190e-25 1.00
* p < 0.01
Tukey test for IBD TPR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES 0.0007 0.0008 0.8668 0.6612852
EQ - R 0.0000 0.0008 0.0000 1.0000000
ES - R −0.0007 0.0008 −0.8668 0.6612852 
## Warning in run_lmer(mmrr_site, .x, filepath = make_lmer_path("mmrr", "site", : 
## All values of IBD FDR are fixed or NA; no model is returned
Linear mixed effect model
IBD MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0010 0.3624 0.3624 1 8.6290K 1.989363e+02 1.1 × 10−44*
Population size 0.0221 1.0570 1.0570 1 8.6290K 5.802786e+02 3.8 × 10−124*
Migration 0.1068 24.6577 24.6577 1 8.6290K 1.353681e+04 0.0*
Selection strength −0.0075 0.1219 0.1219 1 8.6290K 6.693473e+01 3.2 × 10−16*
Spatial autocorrelation −0.0002 0.0001 0.0001 1 8.6290K 6.310007e-02 0.80
Environmental correlation 0.0012 0.0033 0.0033 1 8.6290K 1.784720e+00 0.18
* p < 0.001
Tukey test for IBD MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES 0.0000 0.0011 −0.0428 0.9989921
EQ - R −0.0038 0.0011 −3.3592 2.3 × 10−3
ES - R −0.0037 0.0011 −3.3164 2.6 × 10−3
Linear mixed effect model
IBE TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0090 23.0011 23.0011 1 6.6670K 259.6127162 2.5 × 10−57*
Population size 0.0028 0.0127 0.0127 1 6.6674K 0.1430862 0.710
Migration −0.0046 0.0309 0.0309 1 6.6673K 0.3491155 0.550
Selection strength 0.0157 0.4098 0.4098 1 6.6673K 4.6251140 0.032**
Spatial autocorrelation 0.0818 9.4689 9.4689 1 6.6681K 106.8752726 7.3 × 10−25*
Environmental correlation −0.0321 1.7169 1.7169 1 6.6671K 19.3781699 1.1 × 10−5*
* p < 0.001
** p < 0.05
Tukey test for IBE TPR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES −0.1357 0.0089 −15.2061 0.0
EQ - R −0.0883 0.0089 −9.8940 2.8 × 10−14
ES - R 0.0474 0.0089 5.3121 3.2 × 10−7
Linear mixed effect model
IBE FDR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0007 0.1970 0.1970 1 8.6290K 12.054216 5.2 × 10−4*
Population size 0.0105 0.2396 0.2396 1 8.6290K 14.663682 1.3 × 10−4*
Migration 0.0378 3.0940 3.0940 1 8.6290K 189.345838 1.2 × 10−42*
Selection strength −0.0047 0.0486 0.0486 1 8.6290K 2.976651 0.085
Spatial autocorrelation −0.0337 2.4503 2.4503 1 8.6290K 149.949919 3.4 × 10−34*
Environmental correlation 0.0073 0.1148 0.1148 1 8.6290K 7.028155 8.0 × 10−3**
* p < 0.001
** p < 0.01
Tukey test for IBE FDR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES −0.0175 0.0034 −5.2053 5.8 × 10−7
EQ - R −0.0066 0.0034 −1.9584 0.1226645
ES - R 0.0109 0.0034 3.2469 3.3 × 10−3
Linear mixed effect model
IBE MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0027 2.7352 2.7352 1 8.6290K 1.622508e+03 0.0*
Population size 0.0014 0.0045 0.0045 1 8.6290K 2.682024e+00 0.10
Migration 0.0071 0.1102 0.1102 1 8.6290K 6.539688e+01 7.0 × 10−16*
Selection strength −0.0001 0.0000 0.0000 1 8.6290K 8.222296e-03 0.93
Spatial autocorrelation 0.0036 0.0284 0.0284 1 8.6290K 1.686173e+01 4.1 × 10−5*
Environmental correlation 0.0062 0.0833 0.0833 1 8.6290K 4.941667e+01 2.2 × 10−12*
* p < 0.001
Tukey test for IBE MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES 0.0004 0.0011 0.3705 0.9271412
EQ - R 0.0049 0.0011 4.5248 1.8 × 10−5
ES - R 0.0045 0.0011 4.1543 9.7 × 10−5

1.2.3 Full plots

2. GDM

2.1 Individual sampling

2.1.1 Summary plots

2.1.2 Linear mixed effects models

## Warning in run_lmer(gdm_ind, .x, filepath = make_lmer_path("gdm", "ind", : 
## All values of IBD TPR are fixed or NA; no model is returned
## Warning in run_lmer(gdm_ind, .x, filepath = make_lmer_path("gdm", "ind", : 
## All values of IBD FDR are fixed or NA; no model is returned
Linear mixed effect model
IBD MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0003 4.9829 4.9829 1 15.3420K 2555.862541 0.0*
Population size 0.0019 0.0142 0.0142 1 15.3420K 7.279726 7.0 × 10−3**
Migration −0.0145 0.8120 0.8120 1 15.3420K 416.506452 2.3 × 10−91*
Selection strength −0.0008 0.0026 0.0026 1 15.3420K 1.311347 0.250
Spatial autocorrelation 0.0008 0.0025 0.0025 1 15.3420K 1.293043 0.260
Environmental correlation 0.0014 0.0074 0.0074 1 15.3420K 3.816871 0.051
* p < 0.001
** p < 0.01
Tukey test for IBD MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G 0.0168 0.0010 16.6615 0.0
ES - R 0.0049 0.0010 4.8334 8.0 × 10−6
ES - T 0.0094 0.0010 9.3011 4.1 × 10−14
G - R −0.0119 0.0010 −11.8249 0.0
G - T −0.0074 0.0010 −7.3615 1.1 × 10−12
R - T 0.0045 0.0010 4.4656 4.7 × 10−5 
## Warning in run_lmer(gdm_ind, .x, filepath = make_lmer_path("gdm", "ind", : 
## All values of env_p_TPR are NA for a level of H ; this parameter is dropped from the model
Linear mixed effect model
IBE TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0009 2.3033 2.3033 1 498.2415 42.0843063 2.1 × 10−10*
Population size −0.1315 0.8938 0.8938 1 451.8375 16.3300295 6.3 × 10−5*
Migration −0.1162 1.0973 1.0973 1 492.1461 20.0498258 9.4 × 10−6*
Selection strength 0.0316 0.1192 0.1192 1 499.4142 2.1784099 0.14
Environmental correlation −0.0218 0.0508 0.0508 1 499.1400 0.9284533 0.34
* p < 0.001
Tukey test for IBE TPR
pairwise ~ sampstrat
Contrast Estimate SE t ratio p
ES - G 0.0633 0.0293 2.1597 0.13606967
ES - R −0.0152 0.0294 −0.5179 0.95477772
ES - T −0.0773 0.0293 −2.6394 0.04243910
G - R −0.0785 0.0294 −2.6743 0.03860818
G - T −0.1406 0.0292 −4.8088 1.2 × 10−5
R - T −0.0621 0.0294 −2.1150 0.14971246
Linear mixed effect model
IBE FDR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0001 0.6559 0.6559 1 14.6290K 67.005997 2.9 × 10−16*
Population size −0.0057 0.1201 0.1201 1 14.6291K 12.268760 4.6 × 10−4*
Migration −0.0032 0.0379 0.0379 1 14.6291K 3.875703 0.049**
Selection strength 0.0020 0.0149 0.0149 1 14.6294K 1.521359 0.220
Spatial autocorrelation 0.0095 0.3276 0.3276 1 14.6292K 33.469328 7.4 × 10−9*
Environmental correlation −0.0026 0.0240 0.0240 1 14.6291K 2.454630 0.120
* p < 0.001
** p < 0.05
Tukey test for IBE FDR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G 0.0044 0.0023 1.9074 0.2248336
ES - R −0.0037 0.0023 −1.5989 0.3791959
ES - T −0.0161 0.0023 −6.9828 1.7 × 10−11
G - R −0.0081 0.0023 −3.5077 2.5 × 10−3
G - T −0.0205 0.0023 −8.9047 2.8 × 10−14
R - T −0.0124 0.0023 −5.3768 4.5 × 10−7
Linear mixed effect model
IBE MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0001 0.3139 0.3139 1 15.3420K 1854.72544 0.0*
Population size −0.0024 0.0220 0.0220 1 15.3420K 129.70282 6.3 × 10−30*
Migration 0.0014 0.0070 0.0070 1 15.3420K 41.59368 1.2 × 10−10*
Selection strength 0.0015 0.0084 0.0084 1 15.3420K 49.43952 2.1 × 10−12*
Spatial autocorrelation 0.0014 0.0076 0.0076 1 15.3420K 44.82430 2.2 × 10−11*
Environmental correlation −0.0011 0.0044 0.0044 1 15.3420K 26.19737 3.1 × 10−7*
* p < 0.001
Tukey test for IBE MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
ES - G −0.0009 0.0003 −3.0951 0.01060546
ES - R −0.0019 0.0003 −6.3196 1.6 × 10−9
ES - T −0.0027 0.0003 −8.9634 2.7 × 10−14
G - R −0.0010 0.0003 −3.2251 6.9 × 10−3
G - T −0.0017 0.0003 −5.8680 2.6 × 10−8
R - T −0.0008 0.0003 −2.6416 0.04111901

2.1.3 Full plots

2.1.4 Failed fits

Occasionally GDM fails to fit a model, in which case an NA value is assigned. Here we check the proportion of NAs (i.e., cases of failed fit) across the simulations:

Proportion of failed full models:

2.2 Site sampling

2.2.1 Summary plots

2.2.2 Linear mixed effects models

Linear mixed effect model
IBD TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0005 0.0811 0.0811 1 7.8090K 30.38402362 3.7 × 10−8*
Population size 0.0007 0.0010 0.0010 1 7.8090K 0.38176437 0.54
Migration −0.0003 0.0001 0.0001 1 7.8090K 0.05418347 0.82
Selection strength −0.0016 0.0052 0.0052 1 7.8090K 1.94232427 0.16
Spatial autocorrelation −0.0015 0.0044 0.0044 1 7.8090K 1.64653123 0.20
Environmental correlation −0.0008 0.0013 0.0013 1 7.8090K 0.50243692 0.48
* p < 0.001
Tukey test for IBD TPR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES −0.0017 0.0014 −1.2089 0.4478540
EQ - R −0.0025 0.0014 −1.7343 0.1924110
ES - R −0.0008 0.0014 −0.5245 0.8593617 
## Warning in run_lmer(gdm_site, .x, filepath = make_lmer_path("gdm", "site", : 
## All values of IBD FDR are fixed or NA; no model is returned
Linear mixed effect model
IBD MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0017 1.0608 1.0608 1 8.4000K 171.818434 7.1 × 10−39*
Population size 0.0154 0.4994 0.4994 1 8.4000K 80.890799 2.9 × 10−19*
Migration 0.0868 15.8373 15.8373 1 8.4000K 2565.095054 0.0*
Selection strength −0.0036 0.0271 0.0271 1 8.4000K 4.382271 0.036**
Spatial autocorrelation −0.0030 0.0191 0.0191 1 8.4000K 3.096860 0.078
Environmental correlation 0.0057 0.0679 0.0679 1 8.4001K 11.001157 9.1 × 10−4*
* p < 0.001
** p < 0.05
Tukey test for IBD MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES −0.0295 0.0021 −14.0721 0.0
EQ - R −0.0288 0.0021 −13.7786 0.0
ES - R 0.0006 0.0021 0.2962 0.9527765 
## Warning in run_lmer(gdm_site, .x, filepath = make_lmer_path("gdm", "site", : 
## All values of env_p_TPR are NA for a level of H ; this parameter is dropped from the model
Linear mixed effect model
IBE TPR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0017 0.0308 0.0308 1 255.6048 2.1991749 0.14
Population size −0.0320 0.0281 0.0281 1 231.6609 2.0046388 0.16
Migration −0.0105 0.0046 0.0046 1 255.3889 0.3271284 0.57
Selection strength −0.0096 0.0056 0.0056 1 256.8676 0.4026111 0.53
Environmental correlation −0.0115 0.0074 0.0074 1 255.6449 0.5268093 0.47
Tukey test for IBE TPR
pairwise ~ sampstrat
Contrast Estimate SE t ratio p
EQ - ES −0.0464 0.0177 −2.6220 0.02503871
EQ - R −0.0345 0.0178 −1.9449 0.12832970
ES - R 0.0119 0.0181 0.6564 0.78892520
Linear mixed effect model
IBE FDR ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number 0.0004 0.0424 0.0424 1 7.6355K 9.259080 2.4 × 10−3*
Population size 0.0026 0.0132 0.0132 1 7.6350K 2.890448 0.089
Migration 0.0022 0.0092 0.0092 1 7.6350K 2.016252 0.160
Selection strength 0.0031 0.0184 0.0184 1 7.6351K 4.019454 0.045**
Spatial autocorrelation 0.0087 0.1444 0.1444 1 7.6352K 31.538566 2.0 × 10−8***
Environmental correlation −0.0037 0.0257 0.0257 1 7.6352K 5.620700 0.018**
* p < 0.01
** p < 0.05
*** p < 0.001
Tukey test for IBE FDR
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES −0.0086 0.0019 −4.5867 1.3 × 10−5
EQ - R −0.0067 0.0019 −3.5419 1.2 × 10−3
ES - R 0.0019 0.0019 0.9936 0.5809158
Linear mixed effect model
IBE MAE ~ nsamp + sampstrat + K + m + phi + H + r + (1 | seed)
Predictors Fixed Effects Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
Sample number −0.0008 0.2456 0.2456 1 8.4000K 637.0438734 1.5 × 10−135*
Population size −0.0004 0.0003 0.0003 1 8.4000K 0.6935302 0.40
Migration 0.0021 0.0093 0.0093 1 8.4000K 24.2065506 8.8 × 10−7*
Selection strength 0.0002 0.0001 0.0001 1 8.4000K 0.2126786 0.64
Spatial autocorrelation 0.0040 0.0339 0.0339 1 8.4000K 87.9145144 8.6 × 10−21*
Environmental correlation −0.0021 0.0090 0.0090 1 8.4000K 23.2593102 1.4 × 10−6*
* p < 0.001
Tukey test for IBE MAE
pairwise ~ sampstrat
Contrast Estimate SE Z ratio p
EQ - ES 0.0006 0.0005 1.1181 0.5028702
EQ - R −0.0003 0.0005 −0.5903 0.8253362
ES - R −0.0009 0.0005 −1.6922 0.2081436

2.2.3 Full plots

2.2.4 Failed fits

Occasionally GDM fails to fit a model, in which case an NA value is assigned. Here we check the proportion of NAs (i.e., cases of failed fit) across the simulations:

Proportion of failed models:

Figures

Comparison of MMRR and GDM

Comparison of average IBE error:

## [1] "MMRR average IBE error: 0.04"
## [1] "GDM average IBE error: 0.02"